Title :
Symmetric residue pyramids - an extension of Burt Laplacian pyramids
Author :
Rakshit, Subrutu ; Nema, Malay K.
Author_Institution :
Centre for Artificial Intelligence & Robotics, Bangalore, India
Abstract :
The Laplacian pyramid was proposed as a compact image code by Burt (1983). However, it is shown that it does not achieve optimal signal compaction due to significant overlap between subbands in the frequency domain. In addition, it also leads to a slightly redundant signal representation. An extension of the Laplacian pyramid is proposed that exploits this redundancy to achieve better signal compaction. In contrast to the unidirectional fine to coarse approach used by all multiscale representations, the proposed signal representation adopts a bi-directional approach. Each subband finally depends on both its coarser and finer neighboring subbands. The representation is symmetric in the sense that each subband is a product of an approximation process (based on a finer approximation) as well as a prediction process (based on a coarser approximation). Applications are in the areas of image characterisation, zooming and compression.
Keywords :
data compression; image coding; image representation; interpolation; prediction theory; transform coding; wavelet transforms; Burt Laplacian pyramids; approximation process; compact image code; frequency domain; image characterisation; image compression; image interpolation; image zooming; multiscale representations; prediction process; redundant signal representation; signal compaction; signal representation; subbands independence; subbands overlapping; symmetric residue pyramids; unidirectional fine to coarse approach; Artificial intelligence; Compaction; Filters; Frequency domain analysis; Image coding; Image reconstruction; Laplace equations; Pixel; Robots; Signal representations;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
Print_ISBN :
0-7803-7663-3
DOI :
10.1109/ICASSP.2003.1199470